bev_ipm的onnx进行PTQ时的yaml文件问题

# Copyright (c) 2020 Horizon Robotics.All Rights Reserved.
#
# The material in this file is confidential and contains trade secrets
# of Horizon Robotics Inc. This is proprietary information owned by
# Horizon Robotics Inc. No part of this work may be disclosed,
# reproduced, copied, transmitted, or used in any way for any purpose,
# without the express written permission of Horizon Robotics Inc.

# 模型转化相关的参数
# ------------------------------------
# model conversion related parameters
model_parameters:
# ONNX浮点网络数据模型文件
# -------------------------------------------------------------------------------------------------------------------
# the model file of floating-point ONNX neural network data
onnx_model: 'ipm.onnx'

# 适用BPU架构
# --------------------------------
# the applicable BPU architecture
march: "bayes"

# 指定模型转换过程中是否输出各层的中间结果，如果为True，则输出所有层的中间输出结果，
# ---------------------------------------------------------------------------------------
# specifies whether or not to dump the intermediate results of all layers in conversion
# if set to True, then the intermediate results of all layers shall be dumped
layer_out_dump: False

# 模型转换输出的结果的存放目录
# ---------------------------------------------------------------------------------------
# the directory in which model conversion results are stored
working_dir: 'model_output'

# 模型转换输出的用于上板执行的模型文件的名称前缀
# -----------------------------------------------------------------------------------------
# model conversion generated name prefix of those model files used for dev board execution
output_model_file_prefix: 'bev_256x704_img_128x128_ipm'

# 模型输入相关参数, 若输入多个节点, 则应使用';'进行分隔, 使用默认缺省设置则写NULL
# -------------------------------------------------------------------------
# model input related parameters,
# please use ";" to seperate when inputting multiple nodes,
# please use NULL for default setting
input_parameters:

# (选填) 模型输入的节点名称, 此名称应与模型文件中的名称一致, 否则会报错, 不填则会使用模型文件中的节点名称
# -------------------------------------------------------------------------------------------------
# (Optional) node name of model input,
# it shall be the same as the name of model file, otherwise an error will be reported,
# the node name of model file will be used when left blank
input_name: 'input.1; points'

# 网络实际执行时，输入给网络的数据格式，包括 nv12/rgb/bgr/yuv444/gray/featuremap,
# ------------------------------------------------------------------------------------------
# the data formats to be passed into neural network when actually performing neural network
# available options: nv12/rgb/bgr/yuv444/gray/featuremap,
# input_type_rt: 'rgb'; 'featuremap'
input_type_rt: 'nv12;featuremap'

# 网络实际执行时输入的数据排布, 可选值为 NHWC/NCHW
# 若input_type_rt配置为nv12，则此处参数不需要配置
# ------------------------------------------------------------------
# the data layout formats to be passed into neural network when actually performing neural network, available options: NHWC/NCHW
# If input_type_rt is configured as nv12, then this parameter does not need to be configured
input_layout_rt: 'NCHW; NHWC'

# 网络训练时输入的数据格式，可选的值为rgb/bgr/gray/featuremap/yuv444
# ---------------------------------------------------------------------
# the data formats in network training
# available options: rgb/bgr/gray/featuremap/yuv444
input_type_train: 'yuv444; featuremap'
# input_type_rt: 'featuremap'; 'featuremap'

# 网络训练时输入的数据排布, 可选值为 NHWC/NCHW
# ---------------------------------------------------------------------
# the data layout in network training, available options: NHWC/NCHW
input_layout_train: 'NCHW; NHWC'

# (选填) 模型网络的输入大小, 以'x'分隔, 不填则会使用模型文件中的网络输入大小，否则会覆盖模型文件中输入大小
# -------------------------------------------------------------------------------------------
# (Optional)the input size of model network, seperated by 'x'
# note that the network input size of model file will be used if left blank
# otherwise it will overwrite the input size of model file
input_shape: '6x3x512x960; 6x128x128x2'

# 网络实际执行时，输入给网络的batch_size, 默认值为1
# ---------------------------------------------------------------------
# the data batch_size to be passed into neural network when actually performing neural network, default value: 1
# input_batch: 1

# 网络输入的预处理方法，主要有以下几种：
# no_preprocess 不做任何操作
# data_mean 减去通道均值mean_value
# data_scale 对图像像素乘以data_scale系数
# data_mean_and_scale 减去通道均值后再乘以scale系数
# -------------------------------------------------------------------------------------------
# preprocessing methods of network input, available options:
# 'no_preprocess' indicates that no preprocess will be made
# 'data_mean' indicates that to minus the channel mean, i.e. mean_value
# 'data_scale' indicates that image pixels to multiply data_scale ratio
# 'data_mean_and_scale' indicates that to multiply scale ratio after channel mean is minused
norm_type: 'data_mean_and_scale; no_preprocess'

# 图像减去的均值, 如果是通道均值，value之间必须用空格分隔
# --------------------------------------------------------------------------
# the mean value minused by image
# note that values must be seperated by space if channel mean value is used
mean_value: 0.485 0.456 0.406;NULL

# 图像预处理缩放比例，如果是通道缩放比例，value之间必须用空格分隔
# ---------------------------------------------------------------------------
# scale value of image preprocess
# note that values must be seperated by space if channel scale value is used
scale_value: 0.229 0.224 0.225 ;NULL

# 模型量化相关参数
# -----------------------------
# model calibration parameters
calibration_parameters:

# 模型量化的参考图像的存放目录，图片格式支持Jpeg、Bmp等格式，输入的图片
# 应该是使用的典型场景，一般是从测试集中选择20~100张图片，另外输入
# 的图片要覆盖典型场景，不要是偏僻场景，如过曝光、饱和、模糊、纯黑、纯白等图片
# 若有多个输入节点, 则应使用';'进行分隔
# -----------------------------------------------------------------------
# the directory where reference images of model quantization are stored
# image formats include JPEG, BMP etc.
# should be classic application scenarios, usually 20~100 images are picked out from test datasets
# in addition, note that input images should cover typical scenarios
# and try to avoid those overexposed, oversaturated, vague,
# pure blank or pure white images
# use ';' to seperate when there are multiple input nodes
cal_data_dir: './calibration_data/calibrate_imgs;./calibration_data/calibrate_points'

# 校准数据二进制文件的数据存储类型，可选值为：float32, uint8
# calibration data binary file save type, available options: float32, uint8
cal_data_type: 'uint8;float32'

# 如果输入的图片文件尺寸和模型训练的尺寸不一致时，并且preprocess_on为true，
# 则将采用默认预处理方法(skimage resize)，
# 将输入图片缩放或者裁减到指定尺寸，否则，需要用户提前把图片处理为训练时的尺寸
# ----------------------------------------------------------------------------------
# In case the size of input image file is different from that of in model training
# and that preprocess_on is set to True,
# shall the default preprocess method(skimage resize) be used
# i.e., to resize or crop input image into specified size
# otherwise user must keep image size as that of in training in advance
# preprocess_on: False

# 模型量化的算法类型，支持default、mix、kl、max、load，通常采用default即可满足要求
# 如不符合预期可先尝试修改为mix 仍不符合预期再尝试kl或max
# 当使用QAT导出模型时，此参数则应设置为load
# 相关参数的技术原理及说明请您参考用户手册中的PTQ原理及步骤中参数组详细介绍部分
# ----------------------------------------------------------------------------------
# The algorithm type of model quantization, support default, mix, kl, max, load, usually use default can meet the requirements.
# If it does not meet the expectation, you can try to change it to mix first. If there is still no expectation, try kl or max again.
# When using QAT to export the model, this parameter should be set to load.
# For more details of the parameters, please refer to the parameter details in PTQ Principle And Steps section of the user manual.
calibration_type: 'skip'

# 编译器相关参数
# ----------------------------
# compiler related parameters
compiler_parameters:

# 编译策略，支持bandwidth和latency两种优化模式;
# bandwidth以优化ddr的访问带宽为目标；
# latency以优化推理时间为目标
# ------------------------------------------------------------------------------------------
# compilation strategy, there are 2 available optimization modes: 'bandwidth' and 'lantency'
# the 'bandwidth' mode aims to optimize ddr access bandwidth
# while the 'lantency' mode aims to optimize inference duration
compile_mode: 'latency'

# 设置debug为True将打开编译器的debug模式，能够输出性能仿真的相关信息，如帧率、DDR带宽占用等
# ------------------------------------------------------------------------------------------
# the compiler's debug mode will be enabled by setting to True
# this will dump performance simulation related information
# such as: frame rate, DDR bandwidth usage etc.
debug: False

# 编译模型指定核数，不指定默认编译单核模型, 若编译双核模型，将下边注释打开即可
# -------------------------------------------------------------------------------------
# specifies number of cores to be used in model compilation
# as default, single core is used as this value left blank
# please delete the "# " below to enable dual-core mode when compiling dual-core model
# core_num: 2

# 优化等级可选范围为O0~O3
# O0不做任何优化, 编译速度最快，优化程度最低,
# O1-O3随着优化等级提高，预期编译后的模型的执行速度会更快，但是所需编译时间也会变长。
# 推荐用O2做最快验证
# ---------------------------------------------------------------------------------------
# optimization level ranges between O0~O3
# O0 indicates that no optimization will be made
# the faster the compilation, the lower optimization level will be
# O1-O3: as optimization levels increase gradually, model execution, after compilation,
# shall become faster while compilation will be prolonged
# it is recommended to use O2 for fastest verification
optimize_level: 'O3'